成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	邱威智 Chiu, Wei-Chih
論文名稱：	以查表方式加速演算式計算運用於牙科放射性像差攝影術前校正 A Look-up Table Strategy to Hasten Evolutionary Computing in Registration of Dental Subtraction Radiography
指導教授：	郭淑美 Guo, Shu-Mei
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 醫學資訊研究所 Institute of Medical Informatics
論文出版年：	2012
畢業學年度：	100
語文別：	英文
論文頁數：	48
中文關鍵詞：	牙科像差放射性影像、基因演算法、查表方式、快速校正
外文關鍵詞：	Dental subtraction radiography, genetic algorithm, lookup table strategy, quickly registration
相關次數：	點閱：109 下載：2
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

目前牙科像差放射性影像的取得，多依靠牙齒印模來固定照相角度關係，以取得具有相似對應之幾何關係的影像。因為牙齒印模裝置保存，消毒滅菌不便，無法用於實際臨床之上。本論文提出一套牙科X光片影像校正之方式，能迅速地達成牙科放射性像差攝影術的實際臨床運用。本文提出的系統分為兩個階段並分別結合兩種不同的進化演算方法，以達到加速運算的效果。第一階段先利用基因演算法來找出各個不同影像對之間最佳的轉換參數。將以基因演算法尋找到的最佳轉換參數記錄下來，形成資料庫，以查表方式減少所需之大量運算時間。第二階段利用爬山法快速收斂的性質，對於這些參數進行微調，以符合新的影像轉換所需。本論文之演算法整合兩者之優點，以求得更快更準確的結果。
實驗選取75對臨床X光片。50對用於建立參數資料庫。另外25對用於測試系統的轉換結果。並以虛擬色彩重疊回原影像呈現差異處。實驗結果與基因演算法及免疫演算法選點校正比較。在時間耗損上，提出之方式可於61秒±8秒內得到結果，而基因演算法則為1,580秒±124秒，免疫演算法為695秒±168秒。校正品質上，本方式之PSNR值為33.08±3.59dB，基因演算法為32.88±3.37dB，免疫演算法為32.84±3.72dB。觀察者在像差影像下觀察之一致性可達84%，對於系統的平均滿意度則為84.7%。本論文提出以查表方式減少校正牙科放射性影像之時間及電腦之運算複雜度，一分鐘即顯示之牙科像差放射線影像於實際臨床有一大突破。

Dental subtraction radiography is accomplished by using a special frame to standardize radiographic geometry. However, storage and sterilization of film holders are exhausting and dentists don’t use in daily practice. This study accomplishes a framework to hasten registration of dental subtraction radiography and subsequent to be used in clinical dental subtraction radiography. The proposed method has two phases and combines two kinds of evolutionary computing to speed up computation. Genetic algorithm (GA) is applied to find the optimal parameters of transform function between two radiographic image pairs. The optimal parameters found by GA are recorded and stored in the database. With look-up table strategy, the database provides excellent initial parameters for hillclimbing algorithm adjusting to optimal solutions in short time.
We choose 75 dental radiographic image pairs for this study. 50 image pairs are randomly assigned to establish the database. The other 25 image pairs are used in testing the performance of proposed system. Subtraction image is psedocoloring superimposed to original image for enhancing inspection of radiographs. The performance of proposed method is compared to GA method and automatic point correspondence method based on artificial immune system algorithm (AIS method). Time requirements for image registration of proposed method, GA method, and AIS method are 61.30±8.4 seconds, 1,580.48±124.22 seconds, and 695.03±168.20 seconds, respectively. Quantitative analysis for registration result is evaluated by calculating the peak signal to noise ratio (PSNR). The PSNRs of proposed method, GA method, and AIS method are 33.08 3.59dB, 32.88 3.37dB, and 32.84 3.72dB, respectively. Interobserver agreement is about 84% agreement to the same alterations on all radiographs under system assisting. Satisfaction questionnaire for clinical assistance is overall about 84.37% satisfactions.

中文摘要....................................................I
Abstract..................................................II
Acknowledgment............................................IV
Table of Contents..........................................V
List of Table............................................VII
List of Figures.........................................VIII
Chapter 1  Introduction....................................1
	1.1  Dental Subtraction Radiograph.................3
	1.2  Motivation....................................5
	1.3  Organization of the Thesis....................5
Chapter 2  Background and Related Work.....................6
	2.1  Preliminary Image Registration................6
	2.1.1  Definition..................................6
	2.1.2  Contribution................................7
	2.1.3  Limitation..................................8
	2.2  Review of Image Registration Method...........8
	2.2.1  Feature based method........................9
	2.2.2  Intensity based method.....................10
	2.3  Related Techniques...........................10
	2.3.1  Registration transformation................11
	2.3.2  Optimal algorithm..........................12
	2.3.2.1  Genetic algorithm........................12
	2.3.2.2  Hillclimbing algorithm...................15
	2.4  Related Research for Comparison..............15
	2.4.1	Feature based method: A case study on AIS 
                method....................................16
	2.4.2	Intensity based method: Case studies on 
                ROI-based down hill simplex method and 
                GA-based automatic retiming method........17
Chapter 3  Proposed Framework.............................20
	3.1  Flowchart of Proposed Framework..............20
	3.2  Method of Proposed Framework.................21
	3.2.1  Training phase.............................21
	3.2.1.1  Transformed function.....................23
	3.2.1.2  Genetic algorithm........................23
	3.2.1.3  Evaluation and database formation........26
	3.2.1.4  Idea of lookup table.....................27
	3.2.2  Testing phase..............................28
	3.3  Performance Evaluation.......................30
	3.3.1  Data.......................................30
	3.3.2  Evaluation indices.........................32
	3.3.3  Image quality..............................34
Chapter 4  Results........................................36
Chapter 5  Conclusions and Future Work....................40
	5.1  Conclusions..................................40
	5.2  Future Work..................................41
Reference ................................................42
Appendix .................................................48

                                    

[1]Benbrahim, M. R., R. Benslimane, and E. Aalloula, “Automatic retiming method based on genetic algorithm for the detection and the follow-up of dental lesions,” Electronic Journal Technical Acoustics, 12, 2004.
[2]Carneiro, L. S., H. A. da Cunha, C. R. Leles, and E. F. Mendonca, “Digital subtraction radiography evaluation of longitudinal bone density changes around immediate loading implants: A pilot study,” Dentomaxillofacial Radiology, vol. 41, pp. 241-7, 2012
[3]Carvalho, F. B., M. Goncalves, and M. Tanomaru-Filho, “Evaluation of chronic periapical lesions by digital subtraction radiography by using Adobe Photoshop CS: A technical report,” Journal of Endodontics, vol. 33, pp. 493-7, 2007.
[4]Carvalho, F. B., P. S. Gonçalves, R. K. Lima, J. M. Guerreiro-Tanomaru, L. C. Rasquin, and M. Tanomaru-Filho, “Use of cone-beam tomography and digital subtraction radiography for diagnosis and evaluation of traumatized teeth treated with endodontic surgery and MTA: A case report,” Dental Traumatology, Early View.
[5]Davis, M., K. M. Allen, and E. Hausmann, “Effects of small angle discrepancies on interpretations of subtraction images,” Oral Surgery, Oral Medicine, Oral Pathology, vol. 78, pp.397-400, 1994.
[6]Delano, E. O., D. Tyndall, J. B. Ludlow, M. Trope, and C. Lost, “Quantitative radiographic follow-up of apical surgery: A radiometric and histologic Correlation,” Journal of Endodontics, vol. 24, pp. 420-6, 1998.
[7]Delibasis, K. K., P. A. Asvestas, and G. K. Matsopoulos, “Automatic point correspondence using an artificial immune system optimization technique for medical image registration,” Computer Medical Imaging Graphics, vol. 35, pp. 31-41, 2011.
[8]Duckworth, P. F., P. F. Judy, J. M. Goodson, and S. S. Socransky, “A method for geometric and densitometric standardization of intraoral radiographs,” Journal of Periodontology, vol. 54, pp. 435-40, 1983.
[9]Fraser, S., “Simulation of genetic systems by automatic digital computers. I. Introduction,” Australian Journal Biological Sciences, vol. 10, pp. 484-91, 1957.
[10]Goldberg, D. E., Genetic Algorithm in Search, Optimization, and Machine Learning: Addison Wesley, 1989.
[11]Goldman, M., A. H. Pearson, and N. Darzenta, “Endodontic success: Who’s reading the radiograph?” Oral Surgery, Oral Medicine, Oral Patholology, vol. 33, pp. 432-7, 1972.
[12]Goldman, M., A. H. Pearson, and N. Darzenta, “Reliability of radiographic interpretation,” Oral Surgery, Oral Medicine, Oral Pathology, vol. 38, pp.287-93, 1974.
[13]Gonzalez, R. C., and R. E. Woods, Digital Image Processing, Addison-Wesley Publishing Company, pp. 173-182, 1992.
[14]Gröndahl, H. G., K. Gröndahl, T. Okano, and R. L. Webber, “Statistical contrast enhancement of subtraction images for radiographic caries diagnosis,” Oral Surgery, Oral Medicine, Oral Pathology, vol. 53, pp. 219-23, 1982.
[15]Gröndahl, H. G., K. Gröndahl, and R. L. Webber, “A digital subtraction technique for dental radiography,” Oral Surgery, Oral Medicine, Oral Pathology, vol. 55, pp. 96 -102, 1983.
[16]Gröndahl, K., H. G. Gröndahl, and R. L. Webber, “Influence of variations in projection geometry on the detectability of periodontal bone lesions: A comparison between subtraction radiography and conventional radiographic technique,” Journal of Clinical Periodontology, vol. 11, pp. 411-20, 1984.
[17]Janssen, P. T., W. H. van Palenstein Helderman, and J. van Aken, “The effect of in-vivo-occurring errors in the reproducibility of radiographs on the use of the subtraction technique,” Journal of Clinical Periodontology, vol. 16, pp. 53-8, 1989.
[18]Kozakiewicz, M., K. Bogusiak, M. Denkowski and M. Hanclik, “Evaluation of two programs developed for dental digital subtraction radiography: A comparison between different methods of geometric alignment,” Computational Methods in Science and Technology, vol. 15, pp. 161-7, 2009.
[19]Kullendorff, B., K. Gröndahl, M. Rohlin, and M. Nilsson, “Subtraction radiography of interradicular bone lesions,” Acta Odontologica Scandinavica, vol. 50, pp. 259-67, 1992.
[20]Lehmann, T. M., H. G. Grondahl, and D. K. Benn, “Computer-based registration for digital subtraction in dental radiology,” Dentomaxillofacial Radiology, vol. 29, pp. 323-46, 2000.
[21]Mañana, G., E. Romero, F. González, “A grid computing approach to subtraction radiography,” presented at the IEEE International Conference on Image Processing, pp. 3225-8, 2006.
[22]Mañana, G., E. Romero, and F. González, “Distributed genetic algorithm for subtraction radiography,” presented at the GECCO '05 Proceedings of the 2005 Workshops on Genetic and Evolutionary Computation, pp. 140-6, 2005.
[23]Michalewiez, Z., Genetic Algorithms + Data Structure = Evolution Programs, Berlin: Springer, 1992.
[24]Mikrogeorgis, G., K. Lyroudia, L. Molyvdas, N. Nikolaidis, and L. Pitas, “Digital radiograph registration and subtraction: A useful tool for the evaluation of the progress of chronic apical periododntitis,” Journal of Endodontics, vol. 30, pp. 513-7, 2004.
[25]Nicopoulou-Karayianni, K., U. Brägger, W. Bürgin, P. M. Nielsen, and N. P. Lang, “Diagnosis of alveolar bone changes with digital subtraction images and convencional radiographs,” Oral Surgery, Oral Medicine, Oral Pathology, vol. 72, pp. 251-6, 1991.
[26]Ono, E., E. Medici Filho, H. Faig Leite, J. L. Tanaka, M. E. De Moraes, and J. C. De Melo Castilho, “Evaluation of simulated external root resorptions with digital radiography and digital subtraction radiography,” American Journal of Orthodontics and Dentofacial Orthopedics, vol. 139, pp. 324-33, 2011.
[27]Orstavik, D., G. Farrants, T. Wahl, and K. Kerekes, “Image analysis of endodontic radiographs: digital subtraction and quantitative densitometry,” Endodontics and Dental Traumatology, vol. 6, pp. 6 -11, 1990.
[28]Ramprasad, P., H. C. Nagaraj, and M. K. Parasuram, “Wavelet based image registration technique for matching dental x-rays,” Proceedings of world academy of science, engineering and technology, vol. 34, pp. 467-70, 2008.
[29]Rudolph, D. J., S. C. White, and N. J. Mankovich, “Influence of geometric distortion and exposure parameters on sensitivity of digital subtraction radiography,” Oral Surgery, Oral Medicine, Oral Pathology, vol. 64, pp. 631-7, 1987.
[30]Rudolph, D. J., S. C. White, “Film-holding instruments for intraoral subtraction radiography,” Oral Surgery, Oral Medicine, Oral Pathology, vol. 65, pp. 767-72, 1988.
[31]Stephanopoulos, G., G. Mikrogeorgis, and K. Lyroudia, “Assessment of simulated internal resorption cavities using digital and digital subtraction radiography: A comparative study,” Dental Traumatology, vol. 27, pp. 344-9, 2011.
[32]Sunku, R., R. Roopesh, P. Kancherla, K. K. Perumalla, P. V. Yudhistar, and V. S. Reddy, “Quantitative digital subtraction radiography in the assessment of external apical root resorption induced by orthodontic therapy: A retrospective study,” Journal of Contempory Dental Practice, vol. 12, pp. 422-8, 2011.
[33]Tewary, S., J. Luzzo, and G. Hartwell, “Endodontic radiography: Who is reading the digital radiograph?” Journal of Endodontics, vol. 37, pp. 919-21, 2011.
[34]Tyndall, D. A., S. F. Kapa, and C. P. Bagnell, “Digital subtraction radiography for detecting cortical and cancellous bone changes in the periapical region,” Journal of Endodontics, vol. 16, pp. 173-6, 1990.
[35]Webber, R. L., U. E. Ruttimann, and R. A. J. Groenhuis, “Computer correction of projections in dental radiographs,” Journal of Dental Research, vol. 63, pp. 1032-6, 1984.
[36]Yi, W. J., M. S. Heo, S. S. Lee, S. C. Choi, S. B. Lee, and K. H. Huh, “Automatic noise robust registration of dental radiographs for implants using strategic local correlation,” presented at the International Congress Series, 1157-1161, 2004.
[37]Yi, W. J., M. S. Heo, S. S. Lee, S. C. Choi, S. B. Lee, and K. H. Huh, “Automatic noise robust registration of radiographs for subtraction using strategic local correlation: An application to radiographs of dental implants,” Computers in Biology and Medicine, vol. 35, pp. 247-58, 2005.
[38]Yoshioka, T., C. Kobayashi, H. Suda, T. Sasaki, “An observation of the healing process of periapical lesions by digital subtraction radiography,” Journal of Endodontics, vol. 28, pp. 589-91, 2002.

校內：2017-08-31公開
校外：2017-08-31公開

簡易檢索 / 詳目顯示

相關論文